[PATCH v1] powerpc/pseries/eeh: Fix pseries_eeh_err_inject

[LEROY Christophe]

Le 22/08/2024 à 10:27, Narayana Murty N a écrit :
> [Vous ne recevez pas souvent de courriers de nnmlinux at linux.ibm.com. Découvrez pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ]
> 
> VFIO_EEH_PE_INJECT_ERR ioctl is currently failing on pseries
> due to missing implementation of err_inject eeh_ops for pseries.
> This patch implements pseries_eeh_err_inject in eeh_ops/pseries
> eeh_ops. Implements support for injecting MMIO load/store error
> for testing from user space.
> 
> The check on PCI error type code is moved to platform code, since
> the eeh_pe_inject_err can be allowed to more error types depending
> on platform requirement.

Seems like it doesn't build with ppc64_defconfig or ppc64le_defconfig, 
see https://github.com/linuxppc/linux-snowpatch/actions/runs/10507805537

Christophe

> 
> Signed-off-by: Narayana Murty N <nnmlinux at linux.ibm.com>
> ---
> 
> Testing:
> -------
> vfio-test [1] by Alex Willamson, was forked and updated to add
> support inject error on pSeries guest and used to test this
> patch[2].
> 
> References:
> ----------
> [1] https://github.com/awilliam/tests
> [2] https://github.com/nnmwebmin/vfio-ppc-tests/tree/vfio-ppc-ex
> ---
>   arch/powerpc/include/asm/eeh.h               |  1 +
>   arch/powerpc/kernel/eeh.c                    |  6 +--
>   arch/powerpc/platforms/pseries/eeh_pseries.c | 39 +++++++++++++++++++-
>   3 files changed, 40 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
> index 91a9fd53254f..96445e1eb28e 100644
> --- a/arch/powerpc/include/asm/eeh.h
> +++ b/arch/powerpc/include/asm/eeh.h
> @@ -308,6 +308,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed);
>   int eeh_pe_configure(struct eeh_pe *pe);
>   int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
>                        unsigned long addr, unsigned long mask);
> +int eeh_debugfs_break_device(struct pci_dev *pdev);
> 
>   /**
>    * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
> diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
> index d03f17987fca..8db11edd65fb 100644
> --- a/arch/powerpc/kernel/eeh.c
> +++ b/arch/powerpc/kernel/eeh.c
> @@ -1537,10 +1537,6 @@ int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
>          if (!eeh_ops || !eeh_ops->err_inject)
>                  return -ENOENT;
> 
> -       /* Check on PCI error type */
> -       if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
> -               return -EINVAL;
> -
>          /* Check on PCI error function */
>          if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
>                  return -EINVAL;
> @@ -1731,7 +1727,7 @@ static const struct file_operations eeh_dev_check_fops = {
>          .read   = eeh_debugfs_dev_usage,
>   };
> 
> -static int eeh_debugfs_break_device(struct pci_dev *pdev)
> +int eeh_debugfs_break_device(struct pci_dev *pdev)
>   {
>          struct resource *bar = NULL;
>          void __iomem *mapped;
> diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
> index b1ae0c0d1187..5ce1e11ca42f 100644
> --- a/arch/powerpc/platforms/pseries/eeh_pseries.c
> +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
> @@ -782,6 +782,43 @@ static int pseries_notify_resume(struct eeh_dev *edev)
> 
>          return 0;
>   }
> +
> +/**
> + * pseries_eeh_err_inject - Inject specified error to the indicated PE
> + * @pe: the indicated PE
> + * @type: error type
> + * @func: specific error type
> + * @addr: address
> + * @mask: address mask
> + * The routine is called to inject specified error, which is
> + * determined by @type and @func, to the indicated PE
> + */
> +static int pseries_eeh_err_inject(struct eeh_pe *pe, int type, int func,
> +                                 unsigned long addr, unsigned long mask)
> +{
> +       struct  eeh_dev *pdev;
> +
> +       /* Check on PCI error type */
> +       if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
> +               return -EINVAL;
> +
> +       switch (func) {
> +       case EEH_ERR_FUNC_LD_MEM_ADDR:
> +       case EEH_ERR_FUNC_LD_MEM_DATA:
> +       case EEH_ERR_FUNC_ST_MEM_ADDR:
> +       case EEH_ERR_FUNC_ST_MEM_DATA:
> +               /* injects a MMIO error for all pdev's belonging to PE */
> +               pci_lock_rescan_remove();
> +               list_for_each_entry(pdev, &pe->edevs, entry)
> +                       eeh_debugfs_break_device(pdev->pdev);
> +               pci_unlock_rescan_remove();
> +               break;
> +       default:
> +               return -ERANGE;
> +       }
> +
> +       return 0;
> +}
>   #endif
> 
>   static struct eeh_ops pseries_eeh_ops = {
> @@ -792,7 +829,7 @@ static struct eeh_ops pseries_eeh_ops = {
>          .reset                  = pseries_eeh_reset,
>          .get_log                = pseries_eeh_get_log,
>          .configure_bridge       = pseries_eeh_configure_bridge,
> -       .err_inject             = NULL,
> +       .err_inject             = pseries_eeh_err_inject,
>          .read_config            = pseries_eeh_read_config,
>          .write_config           = pseries_eeh_write_config,
>          .next_error             = NULL,
> --
> 2.45.2
>